Title of article :
Signature Codes for Energy-Efficient Data Movement in On-chip Networks
Author/Authors :
Dehyadegari ، Masoud Computer Engineering Department - K. N. Toosi University of Technology
Abstract :
Onchip networks provide a scalable infrastructure for moving data among cores in manycore systems. In future technologies, significant amounts of dynamic energy are dissipated for data movement on onchip links. This paper proposes SigNoC, a predictable approach via signature encoding and transition signaling to reduce switching activity on links. Also, we show that link energy dominates in future technologies. SigNoC makes the switching activity proportional to the number of 1s per data in the source by using transition signaling. We estimate the energy of each packet at the source of routing in NoC. Therefore, we reduce the number of 1s for high energy packets through signature coding in the source. SigNoC mechanism encodes the packets once at the source and decodes them at the destination only; therefore, it has virtually no impact on performance. Simulation results on NAS and Phoenix benchmark suits on 4X4 NoC indicate that SigNoC achieves an average of 28% reduction in the overall NoC energy.
Keywords :
Interconnection Networks , Network on Chip , Data Movement , Coding
Journal title :
Journal of Computing and Security
Journal title :
Journal of Computing and Security